Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the preposition "at" followed by a numeric value

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "at" followed by a numerical value, indicating locations or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aceutical
    -0.84
    Ts
    -0.60
    bender
    -0.60
    HTTP
    -0.60
    Russ
    -0.58
    adoes
    -0.58
    Ds
    -0.57
    idav
    -0.56
    tions
    -0.56
    NESS
    -0.55
    POSITIVE LOGITS
     least
    1.21
    yp
    0.99
     odds
    0.92
    onement
    0.87
     fault
    0.83
     logger
    0.83
    oned
    0.82
    roph
    0.82
     pains
    0.81
    abase
    0.79
    Act Density 0.087%

    No Known Activations